Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.8993. Min Act: -0.1700
Data Index: 8348061 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.8358. Min Act: -0.1699
Data Index: 8812247 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.7721. Min Act: -0.1700
Data Index: 6167738 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.7402. Min Act: -0.1700
Data Index: 3786249 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.7402. Min Act: -0.1700
Data Index: 2178730 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.7082. Min Act: -0.1698
Data Index: 2480603 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6922. Min Act: -0.1689
Data Index: 3758280 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6762. Min Act: -0.1700
Data Index: 7923089 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6762. Min Act: -0.1700
Data Index: 2536219 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6762. Min Act: -0.1699
Data Index: 2545294 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6762. Min Act: -0.1700
Data Index: 7761960 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6602. Min Act: -0.1700
Data Index: 2920303 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6602. Min Act: -0.1700
Data Index: 5750796 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6441. Min Act: -0.1696
Data Index: 7087974 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6281. Min Act: -0.1700
Data Index: 7700091 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6441. Min Act: -0.1700
Data Index: 5332906 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6441. Min Act: -0.1700
Data Index: 3346732 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6281. Min Act: -0.1700
Data Index: 8792480 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6281. Min Act: -0.1700
Data Index: 1182721 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8993. Min Range: -2.8993
Max Act: 2.6281. Min Act: -0.1700
Data Index: 7367532 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19